Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4744 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.2280. Min Act: -0.0001

Data Index: 1349729 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1939. Min Act: -0.0001

Data Index: 639755 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.2002. Min Act: -0.0001

Data Index: 94194 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1876. Min Act: -0.0001

Data Index: 792124 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1740. Min Act: -0.0001

Data Index: 578175 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1773. Min Act: -0.0001

Data Index: 861558 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1763. Min Act: -0.0001

Data Index: 445697 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1750. Min Act: -0.0001

Data Index: 1143997 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1264239 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1753. Min Act: -0.0001

Data Index: 1057445 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1759. Min Act: -0.0001

Data Index: 141707 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1564. Min Act: -0.0001

Data Index: 628514 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1631. Min Act: -0.0001

Data Index: 25701 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1353. Min Act: -0.0001

Data Index: 1008373 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1382. Min Act: -0.0001

Data Index: 542457 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1383. Min Act: -0.0001

Data Index: 887285 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1375. Min Act: -0.0001

Data Index: 239912 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1416. Min Act: -0.0001

Data Index: 53119 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1352. Min Act: -0.0001

Data Index: 662548 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.2280. Min Range: -0.2280

Max Act: 0.1313. Min Act: -0.0001

Data Index: 71946 (C4 (Web Text))

Max Activating Token Index: 573